Recommendation method combining multi-class untrust relation based on collaborative filtering

A collaborative filtering and recommendation method technology, applied in the field of recommendation systems, can solve problems affecting the development of collaborative filtering recommendation methods

Inactive Publication Date: 2016-01-27
BEIHANG UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, problems such as cold start and data sparsity have affected the further development of collaborative filtering recommendation methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Recommendation method combining multi-class untrust relation based on collaborative filtering
  • Recommendation method combining multi-class untrust relation based on collaborative filtering
  • Recommendation method combining multi-class untrust relation based on collaborative filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Embodiments of the present invention will now be described with reference to the accompanying drawings.

[0030] 1. User preference information for categories

[0031] Step ①: Eliminate the category of the item (such as movies, clothes, electrical appliances, etc.) to define the category of the recommended method;

[0032] Step ②: Combine figure 1 As shown in the input scoring matrix, the number of items belonging to category k in the scoring behavior generated by user u and the number of all items in the scoring behavior generated by user u are obtained from the input scoring matrix. The ratio of the number of rating actions to the total number of items for which users generate rating actions, specifically:

[0033] f u ( k ) = n u ( k ) ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a recommendation method combining multi-class untrust relation based on collaborative filtering, and the method comprises the steps: (1) selecting the class information of an item as the class of the method; (2) calculating the user's preference degree for certain class; (3) calculating the user's influence in a trusted network; (4) obtaining a user's preference information matrix and an implicit factor matrix of the item through a scoring matrix; (5) maximizing the difference among preference information of untrust users through the trusted network; (6) forming a formalized representation of the method provided by the invention through combining step (4) and step (5); (7) obtaining the optimal solutions of the user's preference information matrix and the implicit factor matrix through gradient descent; (8) generating recommendation results. The method effectively employs the untrust relation among users in the trusted network to be integrated with user-item scoring data information, thereby achieving a purpose of improving the recommendation precision.

Description

technical field [0001] The invention belongs to the technical field of recommendation systems, and in particular relates to a collaborative filtering recommendation system combined with a social network, which is suitable for a recommendation method that effectively utilizes the non-trust relationship between users in the social network. Background technique [0002] The personalized recommendation service is user-centered, based on understanding user preferences, and provides users with customized personalized information presentation services. It is also an effective way to extract the information needed by users from massive Internet resources. Traditional recommendation methods include content-based recommendation and collaborative filtering recommendation methods. The collaborative filtering recommendation method is widely used in large-scale recommendation systems because of its simple and easy-to-understand characteristics. However, problems such as cold start and da...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q50/00
Inventor 欧阳元新郑曜曜荣文戈熊璋
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap